public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src/ggml-virtgpu
History
Ruben Ortlam d9589688cb llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 
* llama: add new default load-mode auto which picks mmap unless a non-Metal iGPU is used

* Update ggml/src/ggml-hexagon/ggml-hexagon.cpp

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

* set mmap_support to false on OpenCL backend

* fix order of load modes

* use -1 for auto

* resolve load mode auto earlier to correctly pick gpu host or cpu memory

* add load mode auto to llama-bench

* bump virtgpu api version, regenerate docs

---------

Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 		2026-08-14 22:16:06 +03:00
..
backend llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
include ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
CMakeLists.txt ggml: new backend for Virglrenderer API Remoting acceleration (v2) (llama/18718) 2026-01-30 15:56:40 +02:00
apir_cs_ggml-rpc-front.cpp ggml-virtgpu: make the code thread safe (llama/19204) 2026-02-08 09:29:10 +02:00
ggml-backend-buffer-type.cpp llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
ggml-backend-buffer.cpp ggml: backend-agnostic tensor parallelism (experimental) (llama/19378) 2026-04-30 11:29:05 +03:00
ggml-backend-device.cpp llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
ggml-backend-reg.cpp ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
ggml-backend.cpp vulkan: add get/set tensor 2d functions (llama/22514) 2026-05-01 13:07:35 +03:00
ggml-remoting.h ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
ggmlremoting_functions.yaml ggml-virtgpu: make the code thread safe (llama/19204) 2026-02-08 09:29:10 +02:00
regenerate_remoting.py ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
virtgpu-apir.h ggml: new backend for Virglrenderer API Remoting acceleration (v2) (llama/18718) 2026-01-30 15:56:40 +02:00
virtgpu-forward-backend.cpp ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
virtgpu-forward-buffer-type.cpp ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
virtgpu-forward-buffer.cpp ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
virtgpu-forward-device.cpp llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
virtgpu-forward-impl.h ggml-virtgpu: improve the reliability of the code (llama/19846) 2026-02-27 20:57:58 +02:00
virtgpu-forward.gen.h llama: add default load-mode auto, which avoids mmap on iGPUs (llama/26081) 2026-08-14 22:16:06 +03:00
virtgpu-shm.cpp ggml-virtgpu: fix circular dependency in headers (llama/22557) 2026-05-14 21:26:48 +03:00
virtgpu-shm.h ggml: new backend for Virglrenderer API Remoting acceleration (v2) (llama/18718) 2026-01-30 15:56:40 +02:00
virtgpu-utils.cpp ggml: new backend for Virglrenderer API Remoting acceleration (v2) (llama/18718) 2026-01-30 15:56:40 +02:00
virtgpu-utils.h ggml: new backend for Virglrenderer API Remoting acceleration (v2) (llama/18718) 2026-01-30 15:56:40 +02:00
virtgpu.cpp ggml-virtgpu: fix circular dependency in headers (llama/22557) 2026-05-14 21:26:48 +03:00
virtgpu.h ggml-virtgpu: fix circular dependency in headers (llama/22557) 2026-05-14 21:26:48 +03:00